Commit
•
7397d8a
1
Parent(s):
477bd01
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ language:
|
|
| 14 |
A reproduced LLaVA LVLM based on Llama-3-8B LLM backbone. Not an official implementation.
|
| 15 |
Please follow my reproduced implementation [LLaVA-Llama-3](https://github.com/Victorwz/LLaVA-Llama-3/) for more details on fine-tuning LLaVA model with Llama-3 as the foundatiaon LLM.
|
| 16 |
|
|
|
|
|
|
|
| 17 |
## Model Details
|
| 18 |
Follows LLavA-1.5 pre-train and supervised fine-tuning pipeline. You do not need to change the LLaVA codebase to accommodate Llama-3.
|
| 19 |
|
|
|
|
| 14 |
A reproduced LLaVA LVLM based on Llama-3-8B LLM backbone. Not an official implementation.
|
| 15 |
Please follow my reproduced implementation [LLaVA-Llama-3](https://github.com/Victorwz/LLaVA-Llama-3/) for more details on fine-tuning LLaVA model with Llama-3 as the foundatiaon LLM.
|
| 16 |
|
| 17 |
+
[Updates]The codebase has been upgraded to llava-next (llava-v1.6). Now it supports the latest llama-3, phi-3, mistral-v0.1-7b models.
|
| 18 |
+
|
| 19 |
## Model Details
|
| 20 |
Follows LLavA-1.5 pre-train and supervised fine-tuning pipeline. You do not need to change the LLaVA codebase to accommodate Llama-3.
|
| 21 |
|